© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7988
    Prev
    Next
    INDEX
    Explanations

    Good documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    The
    0.64
    lhe
    0.62
    the
    0.60
    In
    0.56
     the
    0.55
     as
    0.53
     The
    0.53
    ت
    0.52
    If
    0.50
    Becoming
    0.50
    POSITIVE LOGITS
     resonator
    0.61
     bleu
    0.56
     munitions
    0.55
     simulator
    0.55
     shader
    0.55
     slats
    0.54
     tarp
    0.53
     carburetor
    0.53
     underside
    0.52
     sacs
    0.52
    Activations Density 0.000%

    No Known Activations